On this video, Josh offers a tour of the rising self-discipline of LLMOps: ideas and practices for steady enchancment of enormous language model-powered purposes.
– Evaluating and evaluating open supply and proprietary fashions
– Workflows and instruments for iteration and immediate administration
– Rules for making use of test-driven improvement to LLMs
Obtain slides and think about lecture notes: https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/llmops/
Intro and outro music made with Riffusion: https://github.com/riffusion/riffusion
Watch the remainder of the LLM Bootcamp movies right here: https://www.youtube.com/playlist?list=PL1T8fO7ArWleyIqOy37OVXsP4hFXymdOZ
00:00 Why LLMOps?
01:55 Selecting your base LLM
04:20 Proprietary LLMs
09:15 Open-source LLMs
14:45 Iteration and immediate administration
22:35 Testing LLMs: Why and why is it laborious?
28:15 Testing LLMs: What works?
35:05 Analysis metrics for LLMs
37:40 Deployment and monitoring
44:35 Check-driven improvement for LLMs
